vulnerability-detection

Tag

Cards List
#vulnerability-detection

Introducing Aardvark: OpenAI’s agentic security researcher

OpenAI Blog ↗ · 2025-10-30 Cached

OpenAI announces Aardvark, an AI-powered agentic security researcher built on GPT-5 that automatically identifies, validates, and patches software vulnerabilities in codebases. The tool integrates with GitHub and development workflows to help security teams discover and fix vulnerabilities at scale.

0 favorites 0 likes
#vulnerability-detection

Introducing CodeMender: an AI agent for code security

Google DeepMind Blog ↗ · 2025-10-23 Cached

Google DeepMind introduces CodeMender, an AI agent that automatically detects and fixes code security vulnerabilities using advanced reasoning and validation techniques. The system has already upstreamed 72 security fixes to open source projects over six months.

0 favorites 0 likes
#vulnerability-detection

Using Gemini 4 Argon to protect against cyber attackers

YouTube AI Channels ↗ · 2026-10-14 Cached

Wiz researchers conducted shadow A/B testing of Gemini 4 in real-world systems, where it detected more than twice as many vulnerabilities as other baseline models while consuming fewer tokens; in the "Hack for Good" project with Google DeepMind, Gemini 4 traced a path from bypassing public file download restrictions to obtaining the master key and escalating privileges to administrator, helping fix high-risk vulnerabilities on government, hospital, and critical infrastructure websites.

0 favorites 0 likes
#vulnerability-detection

Block on Finding and Fixing Security Risks with OpenAI

YouTube AI Channels ↗ · 2026-10-14 Cached

Block shared how it uses OpenAI’s AI capabilities to discover and fix software security risks—the tool goes beyond statically scanning code to reason about attack patterns, cross trust boundaries, and chain together multistep attacks, revealing complete, end-to-end compromise paths while helping pinpoint issues, identify owners, suggest patches, and verify that fixes are effective.

0 favorites 0 likes
#vulnerability-detection

Aug 13, 2026Frontier Red TeamPatterns and problems in emerging multiagent systems

Anthropic Research ↗ · 2026-08-13 Cached

Anthropic's Frontier Red Team explores behavioral tendencies in frontier models that could cause unexpected systemic failures in multiagent systems, and tests coordinating agent swarms for vulnerability detection.

0 favorites 0 likes
#vulnerability-detection

usestrix/strix

GitHub Trending (daily) ↗ · 2026-06-28 Cached

Strix is an open-source AI agent toolkit that autonomously hacks applications to find and fix vulnerabilities, providing validated proof-of-concepts without false positives.

0 favorites 0 likes
#vulnerability-detection

An Initiative to Secure the World's Software | Project Glasswing

YouTube AI Channels ↗ · 2026-05-08 Cached

Anthropic has launched Project Glasswing, leveraging its advanced Claude Mythos model to help critical software organizations identify and fix vulnerabilities, with the goal of enhancing global software security through collective defense.

0 favorites 0 likes
← Previous
← Back to home

Submit Feedback